Detection of cavitation in centrifugal pumps is critical in their condition monitoring. In order to detect cavitation more accurately and confidently, more advanced signal processing techniques are needed. For the classification of a pump conditions based on the outputs of these techniques, advanced machine learning techniques are needed. In this research, an automatic system for cavitation detection is proposed based on machine learning. Bispectral analysis is used for analyzing the vibration signals. The resulting bispectrum images are given to convolutional neural networks (CNNs) as inputs. The CNNs are a pretrained AlexNet and a pretrained GoogleNet, which are used in this application through transfer learning. On the contrary, a laboratory test setup is used for generating controlled cavitation in a centrifugal pump. The suggested algorithm is implemented on the vibration dataset acquired from the laboratory pump test setup. The results show that the cavitation state of the pump can be detected accurately using this system without any need to image processing or feature extraction.

中文翻译：

---

基于振动双谱和迁移学习的离心泵空化分析

检测离心泵中的气穴现象对其状态监测至关重要。为了更准确、更自信地检测空化现象，需要更先进的信号处理技术。为了根据这些技术的输出对泵状况进行分类，需要先进的机器学习技术。在这项研究中，提出了一种基于机器学习的空化检测自动系统。双谱分析用于分析振动信号。生成的双谱图像作为输入提供给卷积神经网络 (CNN)。CNN 是预训练的 AlexNet 和预训练的 GoogleNet，它们通过迁移学习在此应用程序中使用。相反，实验室测试装置用于在离心泵中产生受控空化。建议的算法是在从实验室泵测试设置中获取的振动数据集上实现的。结果表明，使用该系统可以准确检测泵的空化状态，无需进行任何图像处理或特征提取。